bpf.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Magnus Karlsson <magnus.karlsson@intel.com>
To: magnus.karlsson@intel.com, bjorn.topel@intel.com, ast@kernel.org,
	daniel@iogearbox.net, netdev@vger.kernel.org,
	jonathan.lemon@gmail.com
Cc: bpf@vger.kernel.org, saeedm@mellanox.com,
	jeffrey.t.kirsher@intel.com, maciej.fijalkowski@intel.com,
	maciejromanfijalkowski@gmail.com
Subject: [PATCH bpf-next 10/12] xsk: remove unnecessary READ_ONCE of data
Date: Mon,  9 Dec 2019 08:56:27 +0100	[thread overview]
Message-ID: <1575878189-31860-11-git-send-email-magnus.karlsson@intel.com> (raw)
In-Reply-To: <1575878189-31860-1-git-send-email-magnus.karlsson@intel.com>

There are two unnecessary READ_ONCE of descriptor data. These are not
needed since the data is written by the producer before it signals
that the data is available by incrementing the producer pointer. As the
access to this producer pointer is serialized and the consumer always
reads the descriptor after it has read and synchronized with the
producer counter, the write of the descriptor will have fully
completed and it does not matter if the consumer has any read tearing.

Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
---
 net/xdp/xsk_queue.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/xdp/xsk_queue.h b/net/xdp/xsk_queue.h
index 7566f64..89e1fbd 100644
--- a/net/xdp/xsk_queue.h
+++ b/net/xdp/xsk_queue.h
@@ -183,7 +183,7 @@ static inline bool xskq_cons_read_addr(struct xsk_queue *q, u64 *addr,
 	while (q->cached_cons != q->cached_prod) {
 		u32 idx = q->cached_cons & q->ring_mask;
 
-		*addr = READ_ONCE(ring->desc[idx]) & q->chunk_mask;
+		*addr = ring->desc[idx] & q->chunk_mask;
 
 		if (umem->flags & XDP_UMEM_UNALIGNED_CHUNK_FLAG) {
 			if (xskq_cons_is_valid_unaligned(q, *addr,
@@ -308,7 +308,7 @@ static inline bool xskq_cons_read_desc(struct xsk_queue *q,
 		struct xdp_rxtx_ring *ring = (struct xdp_rxtx_ring *)q->ring;
 		u32 idx = q->cached_cons & q->ring_mask;
 
-		*desc = READ_ONCE(ring->desc[idx]);
+		*desc = ring->desc[idx];
 		if (xskq_cons_is_valid_desc(q, desc, umem))
 			return true;
 
-- 
2.7.4


  parent reply	other threads:[~2019-12-09  7:57 UTC|newest]

Thread overview: 22+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-12-09  7:56 [PATCH bpf-next 00/12] xsk: clean up ring access functions Magnus Karlsson
2019-12-09  7:56 ` [PATCH bpf-next 01/12] xsk: eliminate the lazy update threshold Magnus Karlsson
2019-12-09  7:56 ` [PATCH bpf-next 02/12] xsk: consolidate to one single cached producer pointer Magnus Karlsson
2019-12-10  0:42   ` Martin Lau
2019-12-10  9:04     ` Magnus Karlsson
2019-12-13 18:04   ` Maxim Mikityanskiy
2019-12-16  8:46     ` Magnus Karlsson
2019-12-19 14:35       ` Maxim Mikityanskiy
2019-12-19 16:21         ` Magnus Karlsson
2019-12-09  7:56 ` [PATCH bpf-next 03/12] xsk: standardize naming of producer ring access functions Magnus Karlsson
2019-12-09  7:56 ` [PATCH bpf-next 04/12] xsk: simplify detection of empty and full rings Magnus Karlsson
2019-12-09  7:56 ` [PATCH bpf-next 05/12] xsk: eliminate the RX batch size Magnus Karlsson
2019-12-09 10:16   ` Sergei Shtylyov
2019-12-09 13:07     ` Magnus Karlsson
2019-12-09  7:56 ` [PATCH bpf-next 06/12] xsk: simplify xskq_nb_avail and xskq_nb_free Magnus Karlsson
2019-12-09  7:56 ` [PATCH bpf-next 07/12] xsk: simplify the consumer ring access functions Magnus Karlsson
2019-12-09  7:56 ` [PATCH bpf-next 08/12] xsk: change names of validation functions Magnus Karlsson
2019-12-09  7:56 ` [PATCH bpf-next 09/12] xsk: ixgbe: i40e: ice: mlx5: xsk_umem_discard_addr to xsk_umem_release_addr Magnus Karlsson
2019-12-09  7:56 ` Magnus Karlsson [this message]
2019-12-09  7:56 ` [PATCH bpf-next 11/12] xsk: add function naming comments and reorder functions Magnus Karlsson
2019-12-09  7:56 ` [PATCH bpf-next 12/12] xsk: use struct_size() helper Magnus Karlsson
2019-12-10  1:02 ` [PATCH bpf-next 00/12] xsk: clean up ring access functions Martin Lau

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=1575878189-31860-11-git-send-email-magnus.karlsson@intel.com \
    --to=magnus.karlsson@intel.com \
    --cc=ast@kernel.org \
    --cc=bjorn.topel@intel.com \
    --cc=bpf@vger.kernel.org \
    --cc=daniel@iogearbox.net \
    --cc=jeffrey.t.kirsher@intel.com \
    --cc=jonathan.lemon@gmail.com \
    --cc=maciej.fijalkowski@intel.com \
    --cc=maciejromanfijalkowski@gmail.com \
    --cc=netdev@vger.kernel.org \
    --cc=saeedm@mellanox.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body. 
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).